面向场景变化的动态自适应同时定位与地图构建

Dynamic adaptive simultaneous localization and mapping technique for scene change

在动态变化的复杂环境中,如何使同时定位与地图构建(SLAM)系统根据场景变化持续可靠地进行定位和地图构建,成为其能否走向实际应用的关键所在,也是目前SLAM研究领域中重点研究和待解决的问题之一.针对这一问题,本文提出了一个可扩展的、面向场景变化的同时定位与地图构建框架—SceneSLAM,支持场景检测和SLAM算法的有效复用和自动化调度;根据当前场景检测结果,动态自适应地调用依赖不同传感器数据的SLAM算法,从而提高SLAM系统适应环境变化和持续稳定工作的能力;在SceneSLAM框架基础之上,提出了能够有效检测室内、室外、黑暗场景的场景检测模型,以及应对光线变化的室内、室外场景的动态自适应SLAM模型;在模型切换时自动地进行坐标转换和尺度转换,从而获得具备全局一致性和尺度一致性的定位与地图构建结果.最后,基于ROS平台实现了一个动态适应场景变化的SLAM原型系统,实验中利用Turtlebot机器人,在室内、室外、黑暗场景中进行实验,验证了本文所提出方法的有效性.

How to make simultaneous localization and mapping(SLAM) system to be robust and reliable in complex application scenarios has been widely regarded as a key part of automatic and practical robots. Robustness of SLAM system is one of the research focuses in SLAM field. To tackle this issue, we present multi-scene SLAM technique in this paper, which is a novel extensible SLAM framework by combing different SLAM systems facilitated by a scene detection method. Firstly, we propose a robust and extensible SLAM framework called SceneSLAM to enhance the self-adaptive performance of current SLAM systems. By model structure design, it is easy to utilize open-source SLAM systems to be SLAM models of SceneSLAM and modify the scene detection models to support complex application scenarios. Based on the scene detection results, it can schedule the SLAM models automatically.Secondly, aiming at indoor, outdoor and dark scene detection problems, we present a scene detection model based on convolutional neural network and Bias filter optimization. Experimental results show that the proposed scene detection model has reliable accuracy and stability in detecting indoor, outdoor and dark scenes. What’s more, considering sensor failure in indoor, outdoor and dark scenes,we design dynamic adaptive SLAM models to handle the issue. Map fusion is performed to achieve globally consistent localization and mapping when SLAM models scheduled. At last but not least, we build up a prototype system based on SceneSLAM to enhance the reliability of existing SLAM systems when the scene changes between indoor, outdoor and dark scenes. This system runs on a TurtleBot robot equipped with a Kinect sensor. The experimental results show that multi-scene SLAM technique proposed in this paper provides an effective solution to enhance the robustness of existing SLAM systems in dynamic environments.